在Scala Spark应用程序中使用Impala JDBC

libraryDependencies += "org.apache.spark" %% "spark-core" % "2.4.7"
libraryDependencies += "org.apache.spark" %% "spark-sql" % "2.4.7"
libraryDependencies += "org.apache.spark" %% "spark-hive" % "2.4.7"
libraryDependencies += "org.apache.hive" % "hive-jdbc" % "2.3.9"

import org.apache.spark.sql.SparkSession
import java.sql.{Connection, DriverManager, ResultSet}

val spark = SparkSession.builder()
  .appName("SparkImpalaJDBCExample")
  .master("local")
  .getOrCreate()

val connection: Connection = DriverManager.getConnection("jdbc:hive2://localhost:10000/default", "", "")

val statement = connection.createStatement()
val resultSet: ResultSet = statement.executeQuery("SELECT * FROM table_name")

while (resultSet.next()) {
  val column1 = resultSet.getString("column1")
  val column2 = resultSet.getInt("column2")
  // 处理结果集数据
}

resultSet.close()
statement.close()
connection.close()